google-trends
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- COMMAND_EXECUTION (SAFE): The skill uses standard Unix utilities (
curl,grep,sed,tail,head,nl) to retrieve and format Google Trends RSS feeds. This is consistent with its stated functionality. - DATA_EXFILTRATION (SAFE): Network activity is restricted to fetching public data from
trends.google.com. There is no evidence of sensitive file access or transmission of private data to external servers. - PROMPT_INJECTION (SAFE): The instructions and examples are focused on the intended use case of market research and trend analysis. No attempts to override agent constraints or extract system prompts were found.
- INDIRECT PROMPT_INJECTION (SAFE): While the skill ingests external data (RSS titles), the processing is limited to text extraction and display. The risk of the agent being influenced by malicious content within trending search titles is inherent to the search/fetch task and is not facilitated by unsafe skill design.
Audit Metadata